Time_Series
-
InstructTime++: Time Series Classification with Multimodal Language Modeling via Implicit Feature Enhancement
2026-01-21 13:12:23Mingyue Cheng, Xiaoyu Tao, Huajian Zhang, Qi Liu, Enhong ChenAbstract
Most existing time series classification methods adopt a discriminative paradigm that maps input sequences directly to one-hot encoded class labels. While effective, this paradigm struggles to incorporate contextual features and fails to capture semantic relationships among classes. To address these limitations, we propose InstructTime, a novel framework that reformulates time series classification as a multimodal generative task. Specifically, continuous numerical sequences, contextual textual features, and task instructions are treated as multimodal inputs, while class labels are generated as textual outputs by tuned language models. To bridge the modality gap, InstructTime introduces a time series discretization module that converts continuous sequences into discrete temporal tokens, together with an alignment projection layer and a generative self-supervised pre-training strategy to enhance cross-modal representation alignment. Building upon this framework, we further propose InstructTime++, which extends InstructTime by incorporating implicit feature modeling to compensate for the limited inductive bias of language models. InstructTime++ leverages specialized toolkits to mine informative implicit patterns from raw time series and contextual inputs, including statistical feature extraction and vision-language-based image captioning, and translates them into textual descriptions for seamless integration. Extensive experiments on multiple benchmark datasets demonstrate the superior performance of InstructTime++.
Abstract (translated)
大多数现有的时间序列分类方法采用了一种判别式范式，该范式直接将输入序列映射为一个由one-hot编码表示的类别标签。尽管这种方法有效，但它难以整合上下文特征，并且无法捕捉类别的语义关系。为了克服这些限制，我们提出了InstructTime，这是一个新的框架，它重新定义时间序列分类为一个多模态生成任务。具体来说，在该框架中，连续数值序列、上下文文本特征和任务指令被视为多模态输入，而类别标签则通过调整过的语言模型生成为文本输出。 为了弥合不同模态之间的鸿沟，InstructTime引入了一个时间序列离散化模块，它将连续的时间序列转换成离散的时间标记。此外，还包括一个对齐投影层和一种增强跨模态表示对齐的生成自监督预训练策略。 在此框架的基础上，我们进一步提出了InstructTime++，该方法通过引入隐式特征建模来扩展InstructTime以弥补语言模型有限的归纳偏差。InstructTime++利用专门工具包从原始时间序列和上下文输入中挖掘出有用的隐式模式，包括统计特征提取以及基于视觉-语言的时间序列描述生成，并将这些模式转化为文本描述进行无缝集成。 在多个基准数据集上的广泛实验表明了InstructTime++的优越性能。
URL
https://arxiv.org/abs/2601.14968
PDF
-
vLinear: A Powerful Linear Model for Multivariate Time Series Forecasting
2026-01-20 09:23:10Wenzhen Yue, Ruohao Guo, Ji Shi, Zihan Hao, Shiyu Hu, Xianghua YingAbstract
In this paper, we present \textbf{vLinear}, an effective yet efficient \textbf{linear}-based multivariate time series forecaster featuring two components: the \textbf{v}ecTrans module and the WFMLoss objective. Many state-of-the-art forecasters rely on self-attention or its variants to capture multivariate correlations, typically incurring $\mathcal{O}(N^2)$ computational complexity with respect to the number of variates $N$. To address this, we propose vecTrans, a lightweight module that utilizes a learnable vector to model multivariate correlations, reducing the complexity to $\mathcal{O}(N)$. Notably, vecTrans can be seamlessly integrated into Transformer-based forecasters, delivering up to 5$\times$ inference speedups and consistent performance gains. Furthermore, we introduce WFMLoss (Weighted Flow Matching Loss) as the objective. In contrast to typical \textbf{velocity-oriented} flow matching objectives, we demonstrate that a \textbf{final-series-oriented} formulation yields significantly superior forecasting accuracy. WFMLoss also incorporates path- and horizon-weighted strategies to focus learning on more reliable paths and horizons. Empirically, vLinear achieves state-of-the-art performance across 22 benchmarks and 124 forecasting settings. Moreover, WFMLoss serves as an effective plug-and-play objective, consistently improving existing forecasters. The code is available at this https URL.
Abstract (translated)
在这篇论文中，我们提出了**vLinear**，这是一种基于线性且有效的多变量时间序列预测器，具有两个组成部分：**vecTrans**模块和WFMLoss目标。许多最先进的预测模型依赖于自注意力机制或其变体来捕捉多变量相关性，这通常会导致相对于变量数量$N$的$\mathcal{O}(N^2)$计算复杂度。为了解决这一问题，我们提出了一个轻量级模块**vecTrans**，该模块使用可学习向量来建模多变量的相关性，从而将复杂度降低到$\mathcal{O}(N)$。值得注意的是，**vecTrans**可以无缝地集成到基于Transformer的预测器中，提供高达5倍的推理加速，并且性能一致提高。 此外，我们引入了WFMLoss（加权流匹配损失）作为目标函数。不同于常见的以速度为导向的流匹配目标函数，我们证明了一种面向最终序列的目标函数形式可以显著提升预测准确性。此外，WFMLoss还集成了路径和时间范围上的加权策略，以便将学习集中在更可靠的路径和时间段上。 在实证研究中，vLinear模型在22个基准测试和124个预测设置中达到了最先进的性能水平。此外，WFMLoss可以作为一个有效的即插即用目标函数来改进现有的预测器，并且始终能够提高现有预测器的性能。代码可在该网址获得：[此处提供URL]。
URL
https://arxiv.org/abs/2601.13768
PDF
-
ChatAD: Reasoning-Enhanced Time-Series Anomaly Detection with Multi-Turn Instruction Evolution
2026-01-20 03:12:37Hui Sun, Chang Xu, Haonan Xie, Hao Li, Yuhao Huang, Chuheng Zhang, Ming Jin, Xiaoguang Liu, Gang Wang, Jiang BianAbstract
LLM-driven Anomaly Detection (AD) helps enhance the understanding and explanatory abilities of anomalous behaviors in Time Series (TS). Existing methods face challenges of inadequate reasoning ability, deficient multi-turn dialogue capability, and narrow generalization. To this end, we 1) propose a multi-agent-based TS Evolution algorithm named TSEvol. On top of it, we 2) introduce the AD reasoning and multi-turn dialogue Dataset TSEData-20K and contribute the Chatbot family for AD, including ChatAD-Llama3-8B, Qwen2.5-7B, and Mistral-7B. Furthermore, 3) we propose the TS Kahneman-Tversky Optimization (TKTO) to enhance ChatAD's cross-task generalization capability. Lastly, 4) we propose a LLM-driven Learning-based AD Benchmark LLADBench to evaluate the performance of ChatAD and nine baselines across seven datasets and tasks. Our three ChatAD models achieve substantial gains, up to 34.50% in accuracy, 34.71% in F1, and a 37.42% reduction in false positives. Besides, via KTKO, our optimized ChatAD achieves competitive performance in reasoning and cross-task generalization on classification, forecasting, and imputation.
Abstract (translated)
LLM驱动的异常检测（AD）有助于增强对时间序列（TS）中异常行为的理解和解释能力。现有的方法面临着推理能力不足、多轮对话能力欠缺以及泛化范围狭窄的问题。为此，我们提出了以下解决方案： 1) 我们提出了一种基于多代理的时间序列演化算法，命名为TSEvol。 2) 在此基础上，我们引入了异常检测推理及多轮对话数据集TSEData-20K，并贡献了一系列用于异常检测的聊天机器人家族，包括ChatAD-Llama3-8B、Qwen2.5-7B和Mistral-7B。 3) 此外，我们提出了时间序列卡恩曼-特沃斯基优化（TS Kahneman-Tversky Optimization, TKTO），以增强ChatAD在跨任务泛化能力上的表现。 4) 最后，我们提出了一种基于LLM的学习型异常检测基准测试LLADBench，用于评估ChatAD及其九个基线模型在七个数据集和任务中的性能。 我们的三个ChatAD模型取得了显著的改进，在准确性方面提高了34.50%，F1得分提升了34.71%，同时将误报率降低了37.42%。此外，通过TKTO优化后的ChatAD在分类、预测及插值等任务上的推理能力和跨任务泛化能力均表现出竞争性水平。
URL
https://arxiv.org/abs/2601.13546
PDF
-
MN-TSG:Continuous Time Series Generation with Irregular Observations
2026-01-20 02:45:03Xu Zhang, Junwei Deng, Chang Xu, Hao Li, Jiang BianAbstract
Time series generation (TSG) plays a critical role in a wide range of domains, such as healthcare. However, most existing methods assume regularly sampled observations and fixed output resolutions, which are often misaligned with real-world scenarios where data are irregularly sampled and sparsely observed. This mismatch is particularly problematic in applications such as clinical monitoring, where irregular measurements must support downstream tasks requiring continuous and high-resolution time series. Neural Controlled Differential Equations (NCDEs) have shown strong potential for modeling irregular time series, yet they still face challenges in capturing complex dynamic temporal patterns and supporting continuous TSG. To address these limitations, we propose MN-TSG, a novel framework that explores Mixture-of-Experts (MoE)-based NCDEs and integrates them with existing TSG models for irregular and continuous generation tasks. The core of MN-TSG lies in a MoE-NCDE architecture with dynamically parameterized expert functions and a decoupled design that facilitates more effective optimization of MoE dynamics. Furthermore, we leverage existing TSG models to learn the joint distribution over the mixture of experts and the generated time series. This enables the framework not only to generate new samples, but also to produce appropriate expert configurations tailored to each sample, thereby supporting refined continuous TSG. Extensive experiments on ten public and synthetic datasets demonstrate the effectiveness of MN-TSG, consistently outperforming strong TSG baselines on both irregular-to-regular and irregular-to-continuous generation tasks.
Abstract (translated)
时间序列生成（TSG）在医疗保健等众多领域中扮演着关键角色。然而，大多数现有方法假设观察数据是规则采样的，并且输出分辨率是固定的，这往往与现实世界场景不一致，在现实世界场景中，数据通常是不规则和稀疏的采样。这种偏差特别令人担忧的应用是在临床监测等领域，其中不规则测量必须支持下游任务所需的连续性和高分辨率的时间序列。神经控制微分方程（NCDEs）显示出强大的潜力来建模不规则时间序列，但仍面临捕捉复杂动态模式以及支持持续TSG方面的挑战。 为了克服这些局限性，我们提出了MN-TSG框架，该框架探索了基于混合专家(MoE)的NCDE架构，并将它们与现有的TSG模型集成在一起，以处理不规则和连续生成任务。MN-TSG的核心是一个具有动态参数化专家功能的MoE-NCDE架构和一个解耦设计，有助于更有效地优化MoE动力学。此外，我们利用现有的时间序列生成模型来学习混合专家及其产生的时间序列之间的联合分布。这不仅使框架能够生成新的样本，还能够为每个样本提供适当的专家配置，从而支持精细的连续TSG。 在十个公开和合成数据集上的广泛实验表明了MN-TSG的有效性，在不规则到规则以及不规则到持续的时间序列生成任务上始终优于强大的基线模型。
URL
https://arxiv.org/abs/2601.13534
PDF
-
A Unified Variational Imputation Framework for Electric Vehicle Charging Data Using Retrieval-Augmented Language Model
Abstract
The reliability of data-driven applications in electric vehicle (EV) infrastructure, such as charging demand forecasting, hinges on the availability of complete, high-quality charging data. However, real-world EV datasets are often plagued by missing records, and existing imputation methods are ill-equipped for the complex, multimodal context of charging data, often relying on a restrictive one-model-per-station paradigm that ignores valuable inter-station correlations. To address these gaps, we develop a novel PRobabilistic variational imputation framework that leverages the power of large lAnguage models and retrIeval-augmented Memory (PRAIM). PRAIM employs a pre-trained language model to encode heterogeneous data, spanning time-series demand, calendar features, and geospatial context, into a unified, semantically rich representation. This is dynamically fortified by retrieval-augmented memory that retrieves relevant examples from the entire charging network, enabling a single, unified imputation model empowered by variational neural architecture to overcome data sparsity. Extensive experiments on four public datasets demonstrate that PRAIM significantly outperforms established baselines in both imputation accuracy and its ability to preserve the original data's statistical distribution, leading to substantial improvements in downstream forecasting performance.
Abstract (translated)
电动汽车（EV）基础设施中数据驱动应用的可靠性，例如充电需求预测，取决于完整且高质量充电数据的存在。然而，在现实世界中的电动汽车数据集经常会出现记录缺失的情况，而现有的数据填补方法对于复杂的多模式充电数据环境来说显得不足，这些方法通常依赖于每个充电站一个模型的限制性范式，忽略了有价值的跨站相关性。 为了解决这些问题，我们开发了一个新颖的概率变分填补框架——PRobabilistic variational imputation framework that leverages the power of large lAnguage models and retrIeval-augmented Memory（PRAIM）。PRAIM 使用预训练的语言模型将异构数据编码为统一的、语义丰富的表示，包括时间序列需求、日历特征和地理空间背景。该框架通过检索增强型记忆动态地从整个充电网络中提取相关示例，使单个统一填补模型能够克服数据稀疏性问题。 在四个公开数据集上进行的广泛实验表明，PRAIM 在填补准确性以及保留原始数据统计分布方面显著超越了现有的基准方法。这导致下游预测性能有了实质性的改进。
URL
https://arxiv.org/abs/2601.13476
PDF
-
A Learnable Wavelet Transformer for Long-Short Equity Trading and Risk-Adjusted Return Optimization
2026-01-19 22:41:31Shuozhe Li, Du Cheng, Leqi LiuAbstract
Learning profitable intraday trading policies from financial time series is challenging due to heavy noise, non-stationarity, and strong cross-sectional dependence among related assets. We propose \emph{WaveLSFormer}, a learnable wavelet-based long-short Transformer that jointly performs multi-scale decomposition and return-oriented decision learning. Specifically, a learnable wavelet front-end generates low-/high-frequency components via an end-to-end trained filter bank, guided by spectral regularizers that encourage stable and well-separated frequency bands. To fuse multi-scale information, we introduce a low-guided high-frequency injection (LGHI) module that refines low-frequency representations with high-frequency cues while controlling training stability. The model outputs a portfolio of long/short positions that is rescaled to satisfy a fixed risk budget, and is optimized directly with a trading objective and risk-aware regularization. Extensive experiments on five years of hourly data across six industry groups, evaluated over ten random seeds, demonstrate that WaveLSFormer consistently outperforms MLP, LSTM and Transformer backbones, with and without fixed discrete wavelet front-ends. On average in all industries, WaveLSFormer achieves a cumulative overall strategy return of $0.607 \pm 0.045$ and a Sharpe ratio of $2.157 \pm 0.166$, substantially improving both profitability and risk-adjusted returns over the strongest baselines.
Abstract (translated)
从金融时间序列中学习具有盈利能力的日内交易策略是一项挑战，因为存在大量噪声、非平稳性和相关资产间的强横截面依赖。我们提出了一种名为**WaveLSFormer**的方法，这是一种基于可学习小波的长短期Transformer模型，它可以同时进行多尺度分解和以收益为导向的决策学习。 具体来说，WaveLSFormer通过一个端到端训练的小波滤波器组生成低频/高频分量，并使用谱正则化器来鼓励稳定的、间隔良好的频率带。为了融合多尺度信息，我们引入了一个低频引导高频注入（LGHI）模块，该模块在控制训练稳定性的同时用高频提示改进低频表示。 模型输出一个包含长短仓位置的资产组合，并对其进行调整以满足固定的风控预算，在直接优化交易目标和风险感知正则化的基础上进行学习。在五个年度每小时数据集上进行了广泛的实验，包括六个行业组，通过十个随机种子评估结果表明，WaveLSFormer在所有行业中均一致优于MLP、LSTM和Transformer骨干模型，无论是否使用固定离散小波前端。在整个行业中，平均而言，WaveLSFormer实现了0.607±0.045的累计策略总收益以及2.157±0.166的夏普比率，在利润性和风险调整后的回报方面相对于最强基线都有显著改善。
URL
https://arxiv.org/abs/2601.13435
PDF
-
Online Continual Learning for Time Series: a Natural Score-driven Approach
2026-01-19 10:31:01Edoardo Urettini, Daniele Atzeni, Ioanna-Yvonni Tsaknaki, Antonio CartaAbstract
Online continual learning (OCL) methods adapt to changing environments without forgetting past knowledge. Similarly, online time series forecasting (OTSF) is a real-world problem where data evolve in time and success depends on both rapid adaptation and long-term memory. Indeed, time-varying and regime-switching forecasting models have been extensively studied, offering a strong justification for the use of OCL in these settings. Building on recent work that applies OCL to OTSF, this paper aims to strengthen the theoretical and practical connections between time series methods and OCL. First, we reframe neural network optimization as a parameter filtering problem, showing that natural gradient descent is a score-driven method and proving its information-theoretic optimality. Then, we show that using a Student's t likelihood in addition to natural gradient induces a bounded update, which improves robustness to outliers. Finally, we introduce Natural Score-driven Replay (NatSR), which combines our robust optimizer with a replay buffer and a dynamic scale heuristic that improves fast adaptation at regime drifts. Empirical results demonstrate that NatSR achieves stronger forecasting performance than more complex state-of-the-art methods.
Abstract (translated)
在线连续学习（OCL）方法能够在不忘记过去知识的情况下适应环境的变化。同样，实时序列预测（OTSF）是现实世界中的一个问题，在这个问题中数据会随时间演变，成功取决于快速适应和长期记忆的能力。实际上，时变和制度转换的预测模型已经得到了广泛的研究，这为在这些场景下使用OCL提供了强大的理论依据。基于最近将OCL应用于OTSF的工作，本文旨在加强时间序列方法与OCL之间的理论和实践联系。 首先，我们将神经网络优化重新定义为参数过滤问题，并展示了自然梯度下降是一种评分驱动的方法，并证明了其信息论上的最优性。然后，我们表明，在使用自然梯度的同时采用Student's t似然函数可以实现有界更新，从而提高对离群值的鲁棒性。最后，我们提出了自然评分驱动重放（NatSR），该方法结合了我们的鲁棒优化器、回放缓存以及动态尺度启发式策略，以在制度漂移期间改善快速适应能力。 实验证据表明，NatSR在预测性能方面优于更复杂的最新方法。
URL
https://arxiv.org/abs/2601.12931
PDF
-
AdaNODEs: Test Time Adaptation for Time Series Forecasting Using Neural ODEs
2026-01-19 09:46:54Ting Dang, Soumyajit Chatterjee, Hong Jia, Yu Wu, Flora Salim, Fahim KawsarAbstract
Test time adaptation (TTA) has emerged as a promising solution to adapt pre-trained models to new, unseen data distributions using unlabeled target domain data. However, most TTA methods are designed for independent data, often overlooking the time series data and rarely addressing forecasting tasks. This paper presents AdaNODEs, an innovative source-free TTA method tailored explicitly for time series forecasting. By leveraging Neural Ordinary Differential Equations (NODEs), we propose a novel adaptation framework that accommodates the unique characteristics of distribution shifts in time series data. Moreover, we innovatively propose a new loss function to tackle TTA for forecasting tasks. AdaNODEs only requires updating limited model parameters, showing effectiveness in capturing temporal dependencies while avoiding significant memory usage. Extensive experiments with one- and high-dimensional data demonstrate that AdaNODEs offer relative improvements of 5.88\% and 28.4\% over the SOTA baselines, especially demonstrating robustness across higher severity distribution shifts.
Abstract (translated)
测试时间自适应（TTA）作为一种有前景的解决方案，能够利用未标记的目标域数据来调整预训练模型以应对新的、未曾见过的数据分布。然而，大多数TTA方法是为独立数据设计的，往往忽略了时间序列数据，并且很少解决预测任务。本文介绍了AdaNODEs，一种专为时间序列预测量身定制的源无关TTA方法。通过利用神经常微分方程（NODEs），我们提出了一种新颖的适应框架，该框架能够容纳时间序列数据中分布变化的独特特征。此外，我们创新性地提出了一个新的损失函数来解决针对预测任务的TTA问题。AdaNODEs只需更新少量模型参数，在捕获时间依赖关系的同时避免了显著的记忆消耗增加。 广泛的实验结果表明，无论是单维还是高维度的数据上，AdaNODEs相较于最先进的基线方法分别提供了5.88%和28.4%的相对改进，尤其是在面对更高严重程度分布变化时表现出更强的鲁棒性。
URL
https://arxiv.org/abs/2601.12893
PDF
-
Distilling Time Series Foundation Models for Efficient Forecasting
2026-01-19 07:32:00Yuqi Li, Kuiye Ding, Chuanguang Yang, Szu-Yu Chen, Yingli TianAbstract
Time Series foundation models (TSFMs) deliver strong forecasting performance through large-scale pretraining, but their large parameter sizes make deployment costly. While knowledge distillation offers a natural and effective approach for model compression, techniques developed for general machine learning tasks are not directly applicable to time series forecasting due to the unique characteristics. To address this, we present DistilTS, the first distillation framework specifically designed for TSFMs. DistilTS addresses two key challenges: (1) task difficulty discrepancy, specific to forecasting, where uniform weighting makes optimization dominated by easier short-term horizons, while long-term horizons receive weaker supervision; and (2) architecture discrepancy, a general challenge in distillation, for which we design an alignment mechanism in the time series forecasting. To overcome these issues, DistilTS introduces horizon-weighted objectives to balance learning across horizons, and a temporal alignment strategy that reduces architectural mismatch, enabling compact models. Experiments on multiple benchmarks demonstrate that DistilTS achieves forecasting performance comparable to full-sized TSFMs, while reducing parameters by up to 1/150 and accelerating inference by up to 6000x. Code is available at: this https URL.
Abstract (translated)
时间序列基础模型（TSFM）通过大规模预训练提供了强大的预测性能，但其庞大的参数规模使得部署成本高昂。虽然知识蒸馏为模型压缩提供了一种自然且有效的方法，但由于时间序列预测的独特特性，通用机器学习任务中开发的技术并不直接适用。为此，我们提出了DistilTS，这是第一个专门针对TSFM设计的知识蒸馏框架。 DistilTS解决了两个关键挑战：（1）预测特有的任务难度差异问题，在这种情况下，均匀加权使得优化主要由较容易的短期地平线主导，而长期地平线则受到更弱的监督；（2）架构差异，这是知识蒸馏中的一般性挑战，为此我们在时间序列预测中设计了一种对齐机制。为克服这些问题，DistilTS引入了基于地平线加权的目标函数以平衡不同地平线之间的学习，并采用一种减少架构不匹配的时间对齐策略，从而实现模型的紧凑化。 在多个基准测试中的实验表明，DistilTS可以达到与全尺寸时间序列基础模型相当的预测性能，同时将参数减少了多达1/150，并且推理速度提高了最多6000倍。代码可在[这里](https://this.http URL)获得。
URL
https://arxiv.org/abs/2601.12785
PDF
-
Patch-Level Tokenization with CNN Encoders and Attention for Improved Transformer Time-Series Forecasting
2026-01-18 16:16:01Saurish NagrathAbstract
Transformer-based models have shown strong performance in time-series forecasting by leveraging self-attention to model long-range temporal dependencies. However, their effectiveness depends critically on the quality and structure of input representations derived from raw multivariate time-series data. This work proposes a two-stage forecasting framework that explicitly separates local temporal representation learning from global dependency modelling. In the first stage, a convolutional neural network (CNN) operates on fixed-length temporal patches to extract short-range temporal dynamics and non-linear feature interactions, producing compact patch-level token embeddings. Token-level self-attention is subsequently applied during representation learning to refine these embeddings by enabling interactions across temporal patches. In the second stage, a Transformer encoder processes the resulting token sequence to model inter-patch temporal dependencies and generate per-patch forecasts. Experiments conducted on synthetic multivariate time-series data with controlled static and dynamic factors demonstrate that the proposed patch-based tokenization strategy achieves competitive forecasting performance compared to convolutional and patch-based Transformer baselines. The results highlight the importance of structured temporal representations and show that decoupling local temporal encoding from global attention-based modelling yields more effective and stable time-series forecasting.
Abstract (translated)
基于Transformer的模型通过利用自注意力机制来建模长期时间依赖性，在时间序列预测中表现出强大的性能。然而，它们的有效性在很大程度上取决于从原始多变量时间序列数据派生的输入表示的质量和结构。这项工作提出了一种两阶段的时间序列预测框架，该框架明确地将局部时间表示学习与全局依赖关系建模分离。在这个框架的第一阶段，卷积神经网络（CNN）用于处理固定长度的时间片段，以提取短范围内的动态变化以及非线性特征交互，并生成紧凑的分片级别标记嵌入。随后，在表示学习过程中应用了令牌级别的自注意力机制，通过使时间片段之间能够相互作用来优化这些嵌入。 在第二阶段，Transformer编码器对由此产生的令牌序列进行处理，以建模跨分片的时间依赖关系并生成每个分片的预测值。实验使用具有可控静态和动态因素的合成多变量时间序列数据集进行，并表明所提出的基于片段的标记化策略相比卷积基线模型和基于片段的Transformer基线模型，在预测性能上具有竞争力。 结果强调了结构化的时序表示的重要性，同时展示了将局部时序编码从全局注意力机制建模中解耦能够获得更有效且稳定的时序预测效果。
URL
https://arxiv.org/abs/2601.12467
PDF
-
IceWatch: Forecasting Glacial Lake Outburst Floods using Multimodal Deep Learning
2026-01-18 09:29:40Zuha Fatima, Muhammad Anser Sohaib, Muhammad Talha, Ayesha Kanwal, Sidra Sultana, Nazia PerwaizAbstract
Glacial Lake Outburst Floods (GLOFs) pose a serious threat in high mountain regions. They are hazardous to communities, infrastructure, and ecosystems further downstream. The classical methods of GLOF detection and prediction have so far mainly relied on hydrological modeling, threshold-based lake monitoring, and manual satellite image analysis. These approaches suffer from several drawbacks: slow updates, reliance on manual labor, and losses in accuracy when clouds interfere and/or lack on-site data. To tackle these challenges, we present IceWatch: a novel deep learning framework for GLOF prediction that incorporates both spatial and temporal perspectives. The vision component, RiskFlow, of IceWatch deals with Sentinel-2 multispectral satellite imagery using a CNN-based classifier and predicts GLOF events based on the spatial patterns of snow, ice, and meltwater. Its tabular counterpart confirms this prediction by considering physical dynamics. TerraFlow models glacier velocity from NASA ITS_LIVE time series while TempFlow forecasts near-surface temperature from MODIS LST records; both are trained on long-term observational archives and integrated via harmonized preprocessing and synchronization to enable multimodal, physics-informed GLOF prediction. Both together provide cross-validation, which will improve the reliability and interpretability of GLOF detection. This system ensures strong predictive performance, rapid data processing for real-time use, and robustness to noise and missing information. IceWatch paves the way for automatic, scalable GLOF warning systems. It also holds potential for integration with diverse sensor inputs and global glacier monitoring activities.
Abstract (translated)
冰川湖突发洪水（GLOFs）在高山地区构成了严重的威胁，对下游社区、基础设施和生态系统造成了危害。传统的GLOF检测与预测方法主要依赖于水文学建模、基于阈值的湖泊监测以及手动分析卫星图像。这些方法存在若干缺点：更新慢、依赖人工劳动，并且当云层遮挡或缺乏现场数据时准确性会下降。 为了解决这些问题，我们提出了IceWatch：一种新的深度学习框架，用于GLOF预测，并结合了空间和时间两个维度的视角。IceWatch中的视觉部分名为RiskFlow，使用基于CNN（卷积神经网络）的分类器处理Sentinel-2多光谱卫星图像，依据雪、冰以及融水的空间模式来预测GLOF事件。其表格对应的组件通过考虑物理动态确认这一预测。 TerraFlow利用NASA ITS_LIVE时间序列数据模型冰川速度，而TempFlow则从MODIS地表温度记录中预测接近地面的温度；二者都基于长期观测档案训练，并通过统一预处理和同步整合来实现多模态、基于物理学信息的GLOF预测。这两个组件共同提供了交叉验证，从而提高了GLOF检测的可靠性和可解释性。 该系统确保了强大的预测性能，快速的数据处理能力以支持实时应用，并具有抗噪能力和缺失信息的鲁棒性。IceWatch为自动化的、可扩展的GLOF预警系统的实现铺平道路，同时还具备与其他传感器输入和全球冰川监测活动集成的可能性。
URL
https://arxiv.org/abs/2601.12330
PDF
-
TimeGMM: Single-Pass Probabilistic Forecasting via Adaptive Gaussian Mixture Models with Reversible Normalization
2026-01-18 07:02:13Lei Liu, Tengyuan Liu, Hongwei Zhao, Jiahui Huang, Ruibo Guo, Bin LiAbstract
Probabilistic time series forecasting is crucial for quantifying future uncertainty, with significant applications in fields such as energy and finance. However, existing methods often rely on computationally expensive sampling or restrictive parametric assumptions to characterize future distributions, which limits predictive performance and introduces distributional mismatch. To address these challenges, this paper presents TimeGMM, a novel probabilistic forecasting framework based on Gaussian Mixture Models (GMM) that captures complex future distributions in a single forward pass. A key component is GMM-adapted Reversible Instance Normalization (GRIN), a novel module designed to dynamically adapt to temporal-probabilistic distribution shifts. The framework integrates a dedicated Temporal Encoder (TE-Module) with a Conditional Temporal-Probabilistic Decoder (CTPD-Module) to jointly capture temporal dependencies and mixture distribution parameters. Extensive experiments demonstrate that TimeGMM consistently outperforms state-of-the-art methods, achieving maximum improvements of 22.48\% in CRPS and 21.23\% in NMAE.
Abstract (translated)
概率时间序列预测对于量化未来不确定性至关重要，在能源和金融等领域有着重要应用。然而，现有的方法通常依赖于计算成本高昂的采样或限制性的参数假设来表征未来的分布，这会限制预测性能并引入分布不匹配问题。为了应对这些挑战，本文提出了TimeGMM，这是一种基于高斯混合模型（GMM）的新颖概率预测框架，在单次前向传递中捕捉复杂的未来分布情况。 TimeGMM的一个关键组件是GRIN（GMM适配的可逆实例归一化），这是一个专门设计用于动态适应时间-概率分布变化的新型模块。该框架集成了一个专用的时间编码器（TE-模块）和条件时间-概率解码器（CTPD-模块），共同捕获时间依赖性和混合分布参数。 广泛的实验表明，TimeGMM在多个基准数据集上始终优于最先进的方法，在CRPS指标上的改进最大可达22.48%，在NMAE指标上的改进最大可达21.23%。
URL
https://arxiv.org/abs/2601.12288
PDF
-
Wavelet-Driven Masked Multiscale Reconstruction for PPG Foundation Models
2026-01-18 01:34:47Megha Thukral, Cyrus Tanade, Simon A. Lee, Juhyeon Lee, Hao Zhou, Keum San Chun, Migyeong Gwak, Viswam Nathan, Md Mahbubur Rahman, Li Zhu, Mehrab Bin Morshed, Subramaniam Venkatraman, Sharanya Arcot DesaiAbstract
Wearable foundation models have the potential to transform digital health by learning transferable representations from large-scale biosignals collected in everyday settings. While recent progress has been made in large-scale pretraining, most approaches overlook the spectral structure of photoplethysmography (PPG) signals, wherein physiological rhythms unfold across multiple frequency bands. Motivated by the insight that many downstream health-related tasks depend on multi-resolution features spanning fine-grained waveform morphology to global rhythmic dynamics, we introduce Masked Multiscale Reconstruction (MMR) for PPG representation learning - a self-supervised pretraining framework that explicitly learns from hierarchical time-frequency scales of PPG data. The pretraining task is designed to reconstruct randomly masked out coefficients obtained from a wavelet-based multiresolution decomposition of PPG signals, forcing the transformer encoder to integrate information across temporal and spectral scales. We pretrain our model with MMR using ~17 million unlabeled 10-second PPG segments from ~32,000 smartwatch users. On 17 of 19 diverse health-related tasks, MMR trained on large-scale wearable PPG data improves over or matches state-of-the-art open-source PPG foundation models, time-series foundation models, and other self-supervised baselines. Extensive analysis of our learned embeddings and systematic ablations underscores the value of wavelet-based representations, showing that they capture robust and physiologically-grounded features. Together, these results highlight the potential of MMR as a step toward generalizable PPG foundation models.
Abstract (translated)
可穿戴基础模型有潜力通过从日常环境中收集的大规模生物信号中学习转移表示来变革数字健康。尽管在大规模预训练方面已经取得了一些进展，但大多数方法忽略了光体积描记图（PPG）信号中的频谱结构，在这种结构中生理节奏跨越多个频率带展开。鉴于许多下游与健康相关的任务依赖于从精细的波形形态到全局节律动态的多尺度特征，我们引入了Masked Multiscale Reconstruction (MMR)用于PPG表示学习——这是一个自我监督预训练框架，明确地从PPG数据的时间-频谱层级中进行学习。预训练的任务旨在重构通过基于小波的多分辨率分解获得并随机屏蔽掉的PPG信号系数，强制转换器编码器在时间与频谱尺度之间整合信息。 我们使用大约1700万个未标记的10秒PPG片段（来自约32,000名智能手表用户）对我们的模型进行MMR预训练。在19个多样化的健康相关任务中的17个，基于大规模可穿戴设备的PPG数据训练的MMR优于或匹敌现有的开源PPG基础模型、时间序列基础模型以及其他自我监督基线方法。我们学习到嵌入物和系统消融分析的广泛研究表明小波表示的价值所在，显示它们能够捕获稳健且生理学上可信的特征。 这些结果共同突显了MMR作为迈向通用化PPG基础模型一步潜力的重要价值。
URL
https://arxiv.org/abs/2601.12215
PDF
-
One-Shot Price Forecasting with Covariate-Guided Experts under Privacy Constraints
2026-01-17 09:13:57Ren He (Tsinghua University), Yinliang Xu (Tsinghua University), Jinfeng Wang (Guangdong Power Grid Co.), Jeremy Watson (University of Canterbury), Jian Song (Tsinghua University)Abstract
Forecasting in power systems often involves multivariate time series with complex dependencies and strict privacy constraints across regions. Traditional forecasting methods require significant expert knowledge and struggle to generalize across diverse deployment scenarios. Recent advancements in pre-trained time series models offer new opportunities, but their zero-shot performance on domain-specific tasks remains limited. To address these challenges, we propose a novel MoE Encoder module that augments pretrained forecasting models by injecting a sparse mixture-of-experts layer between tokenization and encoding. This design enables two key capabilities: (1) trans forming multivariate forecasting into an expert-guided univariate task, allowing the model to effectively capture inter-variable relations, and (2) supporting localized training and lightweight parameter sharing in federated settings where raw data cannot be exchanged. Extensive experiments on public multivariate datasets demonstrate that MoE-Encoder significantly improves forecasting accuracy compared to strong baselines. We further simulate federated environments and show that transferring only MoE-Encoder parameters allows efficient adaptation to new regions, with minimal performance degradation. Our findings suggest that MoE-Encoder provides a scalable and privacy-aware extension to foundation time series models.
Abstract (translated)
电力系统中的预测通常涉及多变量时间序列，这些序列具有复杂的依赖关系，并且在不同地区之间存在严格的隐私约束。传统的预测方法需要大量的专业知识，并且难以泛化到各种部署场景中。最近，在预训练的时间序列模型方面取得了进展，这为预测任务提供了新的机会，但它们在特定领域的零样本性能仍然有限。 为了应对这些挑战，我们提出了一种新颖的MoE（混合专家）编码器模块，该模块通过在标记化和编码之间注入一个稀疏的混合专家层来增强预训练的预测模型。这种设计实现了两个关键功能：(1) 将多变量预测任务转化为由专家指导的单变量任务，从而使模型能够有效地捕捉变量之间的关系；(2) 支持联邦设置中的本地化培训和轻量级参数共享，在此情况下原始数据不能交换。 在公共多变量数据集上的广泛实验表明，与强大的基线相比，MoE-Encoder显著提高了预测准确性。我们进一步模拟了联邦环境，并展示了仅传输MoE-Encoder的参数就可以高效地适应新区域，同时保持性能下降最小化。我们的发现表明，MoE-Encoder为基础时间序列模型提供了一个可扩展且隐私意识增强的扩展方式。
URL
https://arxiv.org/abs/2601.11977
PDF
-
TF-CoDiT: Conditional Time Series Synthesis with Diffusion Transformers for Treasury Futures
2026-01-17 02:27:56Yingxiao Zhang, Jiaxin Duan, Junfu Zhang, Ke FengAbstract
Diffusion Transformers (DiT) have achieved milestones in synthesizing financial time-series data, such as stock prices and order flows. However, their performance in synthesizing treasury futures data is still underexplored. This work emphasizes the characteristics of treasury futures data, including its low volume, market dependencies, and the grouped correlations among multivariables. To overcome these challenges, we propose TF-CoDiT, the first DiT framework for language-controlled treasury futures synthesis. To facilitate low-data learning, TF-CoDiT adapts the standard DiT by transforming multi-channel 1-D time series into Discrete Wavelet Transform (DWT) coefficient matrices. A U-shape VAE is proposed to encode cross-channel dependencies hierarchically into a latent variable and bridge the latent and DWT spaces through decoding, thereby enabling latent diffusion generation. To derive prompts that cover essential conditions, we introduce the Financial Market Attribute Protocol (FinMAP) - a multi-level description system that standardizes daily$/$periodical market dynamics by recognizing 17$/$23 economic indicators from 7/8 perspectives. In our experiments, we gather four types of treasury futures data covering the period from 2015 to 2025, and define data synthesis tasks with durations ranging from one week to four months. Extensive evaluations demonstrate that TF-CoDiT can produce highly authentic data with errors at most 0.433 (MSE) and 0.453 (MAE) to the ground-truth. Further studies evidence the robustness of TF-CoDiT across contracts and temporal horizons.
Abstract (translated)
扩散变换器（Diffusion Transformers，简称DiT）在合成股票价格和订单流等金融时间序列数据方面取得了重要成就。然而，在合成国债期货数据方面的表现仍鲜有研究。本工作着重于国债期货数据的特点，包括其低交易量、市场依赖性和多变量之间的分组相关性。为了克服这些挑战，我们提出了TF-CoDiT——第一个用于语言控制的国债期货合成的DiT框架。 为促进在低数据环境下的学习能力，TF-CoDiT通过将多通道1-D时间序列转换为离散小波变换（DWT）系数矩阵来调整标准DiT。此外，本工作提出了一种U形变量子系统，用于分层次编码跨通道依赖性到潜在变量中，并通过解码过程在潜在空间和DWT空间之间架起桥梁，从而实现潜在扩散生成。 为了推导覆盖关键条件的提示，我们引入了金融市场属性协议（Financial Market Attribute Protocol，简称FinMAP）——这是一个多级描述系统，通过对7/8个视角中的17/23种经济指标进行识别来标准化每日和周期性的市场动态变化。 在实验中，我们收集了从2015年到2025年的四类国债期货数据，并定义了持续时间从一周至四个月的数据合成任务。广泛的评估显示，TF-CoDiT可以生成与真实情况误差不超过0.433（均方差）和0.453（平均绝对误差）的高度逼真数据。进一步的研究证明了TF-CoDiT在不同合同及时间范围内的鲁棒性。
URL
https://arxiv.org/abs/2601.11880
PDF
-
Wetland mapping from sparse annotations with satellite image time series and temporal-aware segment anything model
2026-01-16 16:10:32Shuai Yuan, Tianwu Lin, Shuang Chen, Yu Xia, Peng Qin, Xiangyu Liu, Xiaoqing Xu, Nan Xu, Hongsheng Zhang, Jie Wang, Peng GongAbstract
Accurate wetland mapping is essential for ecosystem monitoring, yet dense pixel-level annotation is prohibitively expensive and practical applications usually rely on sparse point labels, under which existing deep learning models perform poorly, while strong seasonal and inter-annual wetland dynamics further render single-date imagery inadequate and lead to significant mapping errors; although foundation models such as SAM show promising generalization from point prompts, they are inherently designed for static images and fail to model temporal information, resulting in fragmented masks in heterogeneous wetlands. To overcome these limitations, we propose WetSAM, a SAM-based framework that integrates satellite image time series for wetland mapping from sparse point supervision through a dual-branch design, where a temporally prompted branch extends SAM with hierarchical adapters and dynamic temporal aggregation to disentangle wetland characteristics from phenological variability, and a spatial branch employs a temporally constrained region-growing strategy to generate reliable dense pseudo-labels, while a bidirectional consistency regularization jointly optimizes both branches. Extensive experiments across eight global regions of approximately 5,000 km2 each demonstrate that WetSAM substantially outperforms state-of-the-art methods, achieving an average F1-score of 85.58%, and delivering accurate and structurally consistent wetland segmentation with minimal labeling effort, highlighting its strong generalization capability and potential for scalable, low-cost, high-resolution wetland mapping.
Abstract (translated)
准确的湿地测绘对于生态系统监测至关重要，但密集的像素级标注成本高昂且实用性差，实际应用通常依赖于稀疏点标记，在这种情况下现有的深度学习模型表现不佳；此外，强烈的季节性和年际间的湿地动态变化进一步使得单一日期的影像不足以应对这些挑战，并导致显著的地图绘制错误。虽然像SAM这样的基础模型从点提示中展示出令人鼓舞的一般化能力，但它们本质上是为静态图像设计的，无法建模时间信息，这在异质性湿地中会导致碎片化的掩膜。 为了克服这些限制，我们提出了WetSAM，这是一个基于SAM的框架，通过双分支设计整合卫星影像的时间序列来进行从稀疏点监督的湿地测绘。其中，一个受时间提示驱动的分支扩展了SAM，利用分层适配器和动态时间聚合来分解湿地特征与物候变化；而空间分支则采用一种受限于时间策略的区域生长方法生成可靠的密集伪标签。双向一致性正则化同时优化两个分支。 在八个全球区域（每个区域约为5,000平方公里）进行广泛的实验后，我们发现WetSAM显著优于现有的最先进的方法，在所有测试区域达到了平均F1分数85.58%，并提供了准确且结构一致的湿地分割结果，而仅需最小化的标注工作量。这强调了其强大的泛化能力以及在大规模低成本高分辨率湿地测绘中的巨大潜力。
URL
https://arxiv.org/abs/2601.11400
PDF
-
The Mini Wheelbot Dataset: High-Fidelity Data for Robot Learning
2026-01-16 16:06:32Henrik Hose, Paul Brunzema, Devdutt Subhasish, Sebastian TrimpeAbstract
The development of robust learning-based control algorithms for unstable systems requires high-quality, real-world data, yet access to specialized robotic hardware remains a significant barrier for many researchers. This paper introduces a comprehensive dynamics dataset for the Mini Wheelbot, an open-source, quasi-symmetric balancing reaction wheel unicycle. The dataset provides 1 kHz synchronized data encompassing all onboard sensor readings, state estimates, ground-truth poses from a motion capture system, and third-person video logs. To ensure data diversity, we include experiments across multiple hardware instances and surfaces using various control paradigms, including pseudo-random binary excitation, nonlinear model predictive control, and reinforcement learning agents. We include several example applications in dynamics model learning, state estimation, and time-series classification to illustrate common robotics algorithms that can be benchmarked on our dataset.
Abstract (translated)
对于不稳定系统的基于学习的控制算法的发展需要高质量的真实世界数据，然而获取专门的机器人硬件仍然是许多研究人员面临的重大障碍。本文介绍了一个全面的动力学数据集，用于开源准对称平衡反应轮独轮车——Mini Wheelbot。该数据集提供了1 kHz同步数据，涵盖了所有机载传感器读数、状态估计以及由运动捕捉系统提供的真实姿态和第三人称视频日志。 为了确保数据的多样性，我们包含了在不同硬件实例和表面上使用各种控制范例进行的不同实验，包括伪随机二进制激励、非线性模型预测控制和强化学习代理。我们还提供了几个示例应用，涵盖了动力学模型学习、状态估计和时间序列分类等领域，以展示可以在此数据集上进行基准测试的常见机器人算法。
URL
https://arxiv.org/abs/2601.11394
PDF
-
FEATHer: Fourier-Efficient Adaptive Temporal Hierarchy Forecaster for Time-Series Forecasting
2026-01-16 14:57:41Jaehoon Lee, Seungwoo Lee, Younghwi Kim, Dohee Kim, Sunghyun SimAbstract
Time-series forecasting is fundamental in industrial domains like manufacturing and smart factories. As systems evolve toward automation, models must operate on edge devices (e.g., PLCs, microcontrollers) with strict constraints on latency and memory, limiting parameters to a few thousand. Conventional deep architectures are often impractical here. We propose the Fourier-Efficient Adaptive Temporal Hierarchy Forecaster (FEATHer) for accurate long-term forecasting under severe limits. FEATHer introduces: (i) ultra-lightweight multiscale decomposition into frequency pathways; (ii) a shared Dense Temporal Kernel using projection-depthwise convolution-projection without recurrence or attention; (iii) frequency-aware branch gating that adaptively fuses representations based on spectral characteristics; and (iv) a Sparse Period Kernel reconstructing outputs via period-wise downsampling to capture seasonality. FEATHer maintains a compact architecture (as few as 400 parameters) while outperforming baselines. Across eight benchmarks, it achieves the best ranking, recording 60 first-place results with an average rank of 2.05. These results demonstrate that reliable long-range forecasting is achievable on constrained edge hardware, offering a practical direction for industrial real-time inference.
Abstract (translated)
时间序列预测在制造业和智能工厂等工业领域中至关重要。随着系统向自动化发展，模型必须能在边缘设备（如PLC、微控制器）上运行，并且这些设备对延迟和内存有严格的限制，这使得参数数量通常只能保持在几千以内。传统的深度架构在这种环境下往往不切实际。为此，我们提出了傅里叶高效自适应时间层次预报器（FEATHER），用于在极其有限的条件下进行准确的长期预测。 FEATHER引入了以下四个关键特性： (i) 极轻量级多尺度分解为频率路径； (ii) 一种共享的密集时间核使用投影-深度卷积-投影结构，不依赖递归或注意力机制； (iii) 频率感知分支门控，根据频谱特征自适应融合表示； (iv) 稀疏周期核通过按周期下采样重建输出以捕捉季节性模式。 FEATHER能够在保持紧凑架构（参数量低至400）的同时超越基准模型。在八个基准测试中，它获得了60项第一的成绩，并且平均排名为2.05。这些结果表明，在受限的边缘硬件上实现可靠的长期预测是可行的，为工业实时推理提供了实际的方向。
URL
https://arxiv.org/abs/2601.11350
PDF
-
MiCA: A Mobility-Informed Causal Adapter for Lightweight Epidemic Forecasting
2026-01-16 08:41:06Suhan Guo, Jiahong Deng, Furao ShenAbstract
Accurate forecasting of infectious disease dynamics is critical for public health planning and intervention. Human mobility plays a central role in shaping the spatial spread of epidemics, but mobility data are noisy, indirect, and difficult to integrate reliably with disease records. Meanwhile, epidemic case time series are typically short and reported at coarse temporal resolution. These conditions limit the effectiveness of parameter-heavy mobility-aware forecasters that rely on clean and abundant data. In this work, we propose the Mobility-Informed Causal Adapter (MiCA), a lightweight and architecture-agnostic module for epidemic forecasting. MiCA infers mobility relations through causal discovery and integrates them into temporal forecasting models via gated residual mixing. This design allows lightweight forecasters to selectively exploit mobility-derived spatial structure while remaining robust under noisy and data-limited conditions, without introducing heavy relational components such as graph neural networks or full attention. Extensive experiments on four real-world epidemic datasets, including COVID-19 incidence, COVID-19 mortality, influenza, and dengue, show that MiCA consistently improves lightweight temporal backbones, achieving an average relative error reduction of 7.5\% across forecasting horizons. Moreover, MiCA attains performance competitive with SOTA spatio-temporal models while remaining lightweight.
Abstract (translated)
准确预测传染病的动态对于公共卫生规划和干预至关重要。人类移动性在塑造疫情空间传播方面起着核心作用，但移动数据往往嘈杂、间接且难以与疾病记录可靠地整合。同时，流行病病例的时间序列通常较短，并以较低的时间分辨率报告。这些条件限制了依赖于清洁而丰富数据的参数密集型移动感知预测模型的有效性。 为此，本文提出了一种轻量级且架构无关的模块——受移动信息启发的因果适配器（Mobility-Informed Causal Adapter, MiCA），用于流行病预测。MiCA 通过因果发现推断移动关系，并通过门控残差混合将其集成到时间序列预测模型中。这一设计使轻量级预测器能够在嘈杂且数据有限的情况下，选择性地利用从移动信息衍生的空间结构，而不引入复杂的图神经网络或全注意力机制等重型关系组件。 在四个真实世界流行病数据集上的广泛实验（包括COVID-19发病率、COVID-19死亡率、流感和登革热）表明，MiCA 在预测时间范围内始终提高了轻量级的时间序列骨干模型的性能，平均相对误差降低了7.5%。此外，在保持轻量级的同时，MiCA 的表现可与最先进的时空模型相媲美。 总的来说，这项工作展示了一种新颖的方法，通过结合因果推理和门控混合机制来改进流行病预测，从而在实际应用中提供了有效的解决方案。
URL
https://arxiv.org/abs/2601.11089
PDF
-
ProbFM: Probabilistic Time Series Foundation Model with Uncertainty Decomposition
2026-01-15 17:02:06Arundeep Chinta, Lucas Vinh Tran, Jay KatukuriAbstract
Time Series Foundation Models (TSFMs) have emerged as a promising approach for zero-shot financial forecasting, demonstrating strong transferability and data efficiency gains. However, their adoption in financial applications is hindered by fundamental limitations in uncertainty quantification: current approaches either rely on restrictive distributional assumptions, conflate different sources of uncertainty, or lack principled calibration mechanisms. While recent TSFMs employ sophisticated techniques such as mixture models, Student's t-distributions, or conformal prediction, they fail to address the core challenge of providing theoretically-grounded uncertainty decomposition. For the very first time, we present a novel transformer-based probabilistic framework, ProbFM (probabilistic foundation model), that leverages Deep Evidential Regression (DER) to provide principled uncertainty quantification with explicit epistemic-aleatoric decomposition. Unlike existing approaches that pre-specify distributional forms or require sampling-based inference, ProbFM learns optimal uncertainty representations through higher-order evidence learning while maintaining single-pass computational efficiency. To rigorously evaluate the core DER uncertainty quantification approach independent of architectural complexity, we conduct an extensive controlled comparison study using a consistent LSTM architecture across five probabilistic methods: DER, Gaussian NLL, Student's-t NLL, Quantile Loss, and Conformal Prediction. Evaluation on cryptocurrency return forecasting demonstrates that DER maintains competitive forecasting accuracy while providing explicit epistemic-aleatoric uncertainty decomposition. This work establishes both an extensible framework for principled uncertainty quantification in foundation models and empirical evidence for DER's effectiveness in financial applications.
Abstract (translated)
时间序列基础模型（TSFMs）在零样本金融预测中表现出众，展现了强大的迁移能力和数据效率。然而，由于不确定性量化的基本限制，它们在金融应用中的采用受到阻碍：目前的方法要么依赖于严格的分布假设，混淆了不同的不确定来源，要么缺乏原则性的校准机制。尽管最近的TSFMs采用了复杂的技巧，如混合模型、Student's t-分布或符合预测，但这些方法未能解决提供基于理论的不确定性分解这一核心挑战。我们首次提出了一种新的基于转换器的概率框架——ProbFM（概率基础模型），该框架利用深度证据回归（DER）来提供具有明确知识论—偶然性分解的原则性不确定性量化。 与现有的预设分布形式或要求采样推理的方法不同，ProbFM通过更高阶的证据学习来学习最优的不确定性表示，并保持单次计算效率。为了严格评估独立于架构复杂性的核心DER不确定性量化方法，我们使用一致的LSTM架构对五种概率方法进行了广泛的受控对比研究：DER、高斯负日志似然（Gaussian NLL）、Student's t-负日志似然(Student's-t NLL)、分位数损失(Quantile Loss)和符合预测(Conformal Prediction)。在加密货币回报预测的评估中，结果表明，尽管提供明确的知识论—偶然性不确定性分解，DER仍能保持竞争力的预测准确性。 这项工作不仅为基础模型中的原则性不确定性量化建立了一个可扩展框架，还提供了DER在金融应用中的有效性的实证证据。
URL
https://arxiv.org/abs/2601.10591
PDF
